Table 1 Binary classification report for logistics regression (LR), decision trees (DT) and support vector machines (SVM) tested on the computational battery compounds data set, encoded using one-hot, Mendeleev and Mendeleev+ encoding
From: Classification of battery compounds using structure-free Mendeleev encodings
Algorithm | Encoding | Metric | Class 0 | Class 1 |
|---|---|---|---|---|
| Â | Â | Precision | 0.981 | 0.970 |
| Â | One-hot | Recall | 0.979 | 0.973 |
| Â | Â | Accuracy | 0.980 | 0.972 |
| Â | Â | Precision | 0.999 | 1.000 |
LR | Mendeleev | Recall | 1.000 | 0.992 |
| Â | Â | Accuracy | 1.000 | 0.996 |
| Â | Â | Precision | 1.000 | 1.000 |
| Â | Mendeleev+ | Recall | 1.000 | 1.000 |
| Â | Â | Accuracy | 1.000 | 1.000 |
| Â | Â | Precision | 0.997 | 0.992 |
| Â | One-hot | Recall | 0.994 | 0.995 |
| Â | Â | Accuracy | 0.996 | 0.994 |
| Â | Â | Precision | 1.000 | 0.992 |
DT | Mendeleev | Recall | 0.999 | 1.000 |
| Â | Â | Accuracy | 1.000 | 0.996 |
| Â | Â | Precision | 1.000 | 1.000 |
| Â | Mendeleev+ | Recall | 1.000 | 1.000 |
| Â | Â | Accuracy | 1.000 | 1.000 |
| Â | Â | Precision | 0.997 | 0.997 |
| Â | One-hot | Recall | 0.998 | 0.995 |
| Â | Â | Accuracy | 0.998 | 0.996 |
| Â | Â | Precision | 1.000 | 1.000 |
SVM | Mendeleev | Recall | 1.000 | 1.000 |
| Â | Â | Accuracy | 1.000 | 1.000 |
| Â | Â | Precision | 1.000 | 1.000 |
| Â | Mendeleev+ | Recall | 1.000 | 1.000 |
| Â | Â | Accuracy | 1.000 | 1.000 |